Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
This work addresses the problem of improving generalization across tasks in reinforcement learning for agents, representing an incremental advancement in representation learning methods.
The paper tackled the challenge of learning diverse shared representations in multi-task reinforcement learning by introducing the Mixture of Orthogonal Experts (MOORE) method, which uses orthogonal representations to capture common structures among tasks and achieved state-of-the-art results on the MetaWorld benchmark.
Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems. To this end, sharing representations plays a fundamental role in capturing both unique and common characteristics of the tasks. Tasks may exhibit similarities in terms of skills, objects, or physical properties while leveraging their representations eases the achievement of a universal policy. Nevertheless, the pursuit of learning a shared set of diverse representations is still an open challenge. In this paper, we introduce a novel approach for representation learning in MTRL that encapsulates common structures among the tasks using orthogonal representations to promote diversity. Our method, named Mixture Of Orthogonal Experts (MOORE), leverages a Gram-Schmidt process to shape a shared subspace of representations generated by a mixture of experts. When task-specific information is provided, MOORE generates relevant representations from this shared subspace. We assess the effectiveness of our approach on two MTRL benchmarks, namely MiniGrid and MetaWorld, showing that MOORE surpasses related baselines and establishes a new state-of-the-art result on MetaWorld.